baokuan-article-analysis

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The script makes hidden/insecure outbound HTTP(S) requests to an untrusted domain and deliberately disables TLS verification and SNI, which is indicative of covert or unsafe network behavior that could be used for exfiltration or covert communication.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). scripts/daily_sector_trends.py 在运行时调用 API_HOST_PATH = "onetotenvip.com/skill/cozeSkill/getWxCozeSkillData" 按用户指定关键词查询并把返回的公众号文章 title/summary/noteLink 等自由文本内容用于生成 report.html。